feat(review): 新增确定性检查前置与结论结构化内核

- checks.py：确定性检查（find_zero_length / find_duplicate_entities 传 window + 纯 Python 派生空文字、未闭合多段线）。问题带 source=deterministic，handle 来自工具/数据本身，不依赖 LLM 回忆 - findings.py：解析 LLM 的 JSON 结论 + handle 交叉校验（引用未知 handle 时保留问题、剥掉 handle、verified=False）+ findings 装配 - config.py：新增 DETERMINISTIC_CHECKS / VALIDATE_HANDLES / CHECK_UNCLOSED_POLYLINES 开关与 ZERO_LENGTH_TOLERANCE / DUP_TOLERANCE / DUP_GROUP_LIMIT 实机验证：find_zero_length / find_duplicate_entities 的 window 参数在基座上生效（schema 未声明，C++ 侧 parseCommonQuery 实际支持）。
2026-10-14 19:53:31 +08:00
1 parent a0ea902b50
commit f6d61f8d07
@@ -0,0 +1,212 @@
+"""`dwg_review.checks` 单元测试：确定性检查前置。"""
+
+from dwg_review import checks
+from dwg_review.checks import (
+    check_duplicate_entities,
+    check_zero_length,
+    derive_from_evidence,
+    make_issue,
+    run_deterministic_checks,
+)
+from dwg_review.mcp_client import McpError, McpToolError
+from tests.fakes import FakeMcpClient, make_ctx, make_evidence, ok_text
+
+QUIET = lambda *a: None  # noqa: E731
+WINDOW = {"min_x": 0.0, "min_y": 0.0, "max_x": 10.0, "max_y": 10.0}
+
+
+# ---------------------------------------------------------------------------
+#  make_issue
+# ---------------------------------------------------------------------------
+def test_make_issue_minimal():
+    issue = make_issue("几何", "medium", "零长度")
+    assert issue == {"category": "几何", "severity": "medium",
+                     "message": "零长度", "source": "deterministic"}
+
+
+def test_make_issue_with_handles():
+    issue = make_issue("几何", "low", "重复", handle="A", handles=["A", "B"])
+    assert issue["handle"] == "A"
+    assert issue["handles"] == ["A", "B"]
+
+
+def test_make_issue_omits_empty_handle():
+    assert "handle" not in make_issue("文字", "low", "空文字", handle=None)
+
+
+# ---------------------------------------------------------------------------
+#  check_zero_length
+# ---------------------------------------------------------------------------
+def test_zero_length_turns_items_into_issues():
+    client = FakeMcpClient(responses={"find_zero_length": ok_text({
+        "total": 2, "returned": 2, "offset": 0,
+        "items": [
+            {"handle": "A1", "type": "LINE", "layer": "0", "length": 0.0},
+            {"handle": "A2", "type": "ARC", "layer": "0", "length": 0.0001},
+        ],
+    })})
+    ctx = make_ctx(client=client)
+    issues = check_zero_length(ctx, WINDOW, tolerance=0.001, limit=200, log=QUIET)
+    assert [i["handle"] for i in issues] == ["A1", "A2"]
+    assert all(i["category"] == "几何" and i["severity"] == "medium" for i in issues)
+
+
+def test_zero_length_skips_items_without_handle():
+    client = FakeMcpClient(responses={"find_zero_length": ok_text(
+        {"items": [{"type": "LINE"}, {"handle": "B1"}]}
+    )})
+    ctx = make_ctx(client=client)
+    assert [i["handle"] for i in check_zero_length(ctx, WINDOW, tolerance=0.001,
+                                                   limit=200, log=QUIET)] == ["B1"]
+
+
+def test_zero_length_passes_window_and_params():
+    client = FakeMcpClient(responses={"find_zero_length": ok_text({"items": []})})
+    ctx = make_ctx(client=client)
+    check_zero_length(ctx, WINDOW, tolerance=0.5, limit=77, log=QUIET)
+    assert client.arguments_of("find_zero_length") == {
+        "window": WINDOW, "tolerance": 0.5, "limit": 77,
+    }
+
+
+def test_zero_length_swallows_tool_error():
+    logs = []
+    client = FakeMcpClient(responses={"find_zero_length": McpToolError("炸了")})
+    ctx = make_ctx(client=client)
+    assert check_zero_length(ctx, WINDOW, tolerance=0.001, limit=200, log=logs.append) == []
+    assert any("find_zero_length 失败" in line for line in logs)
+
+
+def test_zero_length_tolerates_non_dict_envelope():
+    client = FakeMcpClient(responses={"find_zero_length": ok_text("oops")})
+    ctx = make_ctx(client=client)
+    assert check_zero_length(ctx, WINDOW, tolerance=0.001, limit=200, log=QUIET) == []
+
+
+# ---------------------------------------------------------------------------
+#  check_duplicate_entities
+# ---------------------------------------------------------------------------
+def test_duplicate_group_becomes_single_issue_with_all_handles():
+    client = FakeMcpClient(responses={"find_duplicate_entities": ok_text({
+        "count": 1,
+        "groups": [{"reason": "identical_geometry", "type": "LINE",
+                    "handles": ["B1", "B2", "B3"]}],
+    })})
+    ctx = make_ctx(client=client)
+    issues = check_duplicate_entities(ctx, WINDOW, tolerance=0.001, group_limit=50, log=QUIET)
+    assert len(issues) == 1  # 一组 = 一个问题
+    assert issues[0]["handle"] == "B1"
+    assert issues[0]["handles"] == ["B1", "B2", "B3"]
+    assert issues[0]["severity"] == "low"
+
+
+def test_duplicate_skips_empty_groups():
+    client = FakeMcpClient(responses={"find_duplicate_entities": ok_text({
+        "groups": [{"handles": []}, {"handles": None}, {"handles": ["C1", "C2"]}],
+    })})
+    ctx = make_ctx(client=client)
+    issues = check_duplicate_entities(ctx, WINDOW, tolerance=0.001, group_limit=50, log=QUIET)
+    assert [i["handle"] for i in issues] == ["C1"]
+
+
+def test_duplicate_passes_group_limit():
+    client = FakeMcpClient(responses={"find_duplicate_entities": ok_text({"groups": []})})
+    ctx = make_ctx(client=client)
+    check_duplicate_entities(ctx, WINDOW, tolerance=0.2, group_limit=9, log=QUIET)
+    assert client.arguments_of("find_duplicate_entities") == {
+        "window": WINDOW, "tolerance": 0.2, "limit": 9,
+    }
+
+
+def test_duplicate_swallows_tool_error():
+    logs = []
+    client = FakeMcpClient(responses={"find_duplicate_entities": McpError(-32603, "x")})
+    ctx = make_ctx(client=client)
+    assert check_duplicate_entities(ctx, WINDOW, tolerance=0.001, group_limit=50,
+                                    log=logs.append) == []
+    assert any("find_duplicate_entities 失败" in line for line in logs)
+
+
+# ---------------------------------------------------------------------------
+#  derive_from_evidence
+# ---------------------------------------------------------------------------
+def test_derive_flags_empty_and_whitespace_texts():
+    ev = make_evidence(texts={"items": [
+        {"handle": "T1", "content": ""},
+        {"handle": "T2", "content": "   "},
+        {"handle": "T3", "content": None},
+        {"handle": "T4", "content": "正常文字"},
+    ]})
+    issues = derive_from_evidence(ev)
+    assert [i["handle"] for i in issues] == ["T1", "T2", "T3"]
+    assert all(i["category"] == "文字" for i in issues)
+
+
+def test_derive_flags_unclosed_polyline():
+    ev = make_evidence(polylines={"items": [
+        {"handle": "P1", "vertex_count": 4, "closed": False},
+        {"handle": "P2", "vertex_count": 4, "closed": True},
+        {"handle": "P3", "vertex_count": 2, "closed": False},
+        {"handle": "P4", "closed": False},
+    ]})
+    issues = derive_from_evidence(ev)
+    assert [i["handle"] for i in issues] == ["P1"]
+
+
+def test_derive_can_disable_unclosed_check():
+    ev = make_evidence(polylines={"items": [{"handle": "P1", "vertex_count": 4, "closed": False}]})
+    assert derive_from_evidence(ev, check_unclosed=False) == []
+
+
+def test_derive_tolerates_missing_sources():
+    assert derive_from_evidence({}) == []
+    assert derive_from_evidence(make_evidence()) == []
+
+
+# ---------------------------------------------------------------------------
+#  run_deterministic_checks
+# ---------------------------------------------------------------------------
+def build_ctx():
+    client = FakeMcpClient(responses={
+        "find_zero_length": ok_text({"items": [{"handle": "Z1", "type": "LINE", "length": 0.0}]}),
+        "find_duplicate_entities": ok_text({"groups": [
+            {"type": "LINE", "handles": ["D1", "D2"]}]}),
+    })
+    return make_ctx(client=client)
+
+
+def test_run_combines_derived_and_mcp():
+    ctx = build_ctx()
+    ev = make_evidence(
+        texts={"items": [{"handle": "T1", "content": ""}]},
+        polylines={"items": [{"handle": "P1", "vertex_count": 3, "closed": False}]},
+    )
+    issues = run_deterministic_checks(ctx, ev, log=QUIET)
+    by_handle = {i.get("handle"): i for i in issues}
+    assert set(by_handle) == {"T1", "P1", "Z1", "D1"}
+    assert by_handle["D1"]["handles"] == ["D1", "D2"]
+
+
+def test_run_passes_window_to_mcp_tools():
+    ctx = build_ctx()
+    ev = make_evidence(bbox=(0.0, 0.0, 10.0, 10.0))
+    run_deterministic_checks(ctx, ev, log=QUIET)
+    assert ctx.client.arguments_of("find_zero_length")["window"] == ev["window"]
+    assert ctx.client.arguments_of("find_duplicate_entities")["window"] == ev["window"]
+
+
+def test_run_without_window_skips_mcp_but_keeps_derived():
+    ctx = build_ctx()
+    ev = make_evidence()
+    ev["window"] = None
+    ev["texts"] = {"items": [{"handle": "T1", "content": ""}]}
+    issues = run_deterministic_checks(ctx, ev, log=QUIET)
+    assert [i["handle"] for i in issues] == ["T1"]
+    assert ctx.client.calls == []
+
+
+def test_run_respects_unclosed_switch(monkeypatch):
+    monkeypatch.setattr(checks.config, "CHECK_UNCLOSED_POLYLINES", False)
+    ctx = build_ctx()
+    ev = make_evidence(polylines={"items": [{"handle": "P1", "vertex_count": 4, "closed": False}]})
+    assert [i["handle"] for i in run_deterministic_checks(ctx, ev, log=QUIET)] == ["Z1", "D1"]